Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition
9 May 2026 – 14 May 2026 · Cape Town, South Africa
661-03-014 ISMRM Abstract

Denoising 3D Motion Corrected Image with a Pretrained 2D U-Net Model

Primary: Acquisition & Reconstruction - Motion Correction: Neuro
Secondary: Acquisition & Reconstruction - Image Reconstruction: AI
661-03-014 · Noise and Artifact Mitigation in MRI · Thursday, 14 May, 1:40 PM–2:35 PM · Digital Posters Row B
Keywords: Brain AI/ML Image Reconstruction Motion Correction Pilot Tone Imaging quality
Accepted
Yajun Li1,2, Cheng-Chieh Cheng3, Jayant Dubey 4, Jeffrey Guenette4,5, Bruno Madore4,5, Lei Qin1,5
1Dana Farber Cancer Institute, Boston, United States of America
2Guangdong Provincial People's Hospital, Southern Medical University, Guangzhou, China
3National Sun Yat-sen University, Kaohsiung, Taiwan
4Brigham and Women's Hospital, Boston, United States of America
5Harvard Medical School, Boston, United States of America
Presenting Author: Jayant Dubey

Synopsis

Motivation:
Goals:
Approach:
Results:
Full abstract & presentation

The full text, figures, and any recorded presentation for this abstract are not shown here. Log in if you are a member or registered attendee with access.

Full abstracts, figures, and presentations for Cape Town - 2026 ISMRM-ISMRT Annual Meeting and Exhibition are available to registered attendees. This content becomes freely available to the public roughly two years after the meeting.

To request or purchase access, contact the ISMRM Central Office at info@ismrm.org.

Log in

References

1. Polak D, Splitthoff DN, Clifford B, Lo WC, Huang SY, Conklin J, et al. Scout accelerated motion estimation and reduction (SAMER). Magn Reson Med. 2022;87(1):163-78. doi:10.1002/mrm.28971 [doi]
2. Brackenier Y, Cordero-Grande L, McElroy S, Tomi-Tricot R, Barbaroux H, Bridgen P, et al. Sequence-agnostic motion-correction leveraging efficiently calibrated Pilot Tone signals. Magn Reson Med. 2024;92(5):1881-97. doi:10.1002/mrm.30161. [doi]
3. Aggarwal HK, Mani MP, Jacob M. MoDL: Model-based deep learning architecture for inverse problems. IEEE transactions on medical imaging. 2018;38(2):394-405. doi:10.1109/TMI.2018.2865356 [doi]
4. Miller Z, Johnson KM. Motion compensated self supervised deep learning for highly accelerated 3D ultrashort Echo time pulmonary MRI. Magn Reson Med. 2023;89(6):2361-75. doi:10.1002/mrm.29586 [doi]
5. Wang Z, Ran M, Yang Z, Yu H, Jing J, Wang T, et al. Generalizable MRI motion correction via compressed sensing equivariant imaging prior. IEEE Transactions on Circuits and Systems for Video Technology. 2024;34(12):12550-67. doi:10.1109/TCSVT.2024.3432751 [doi]
6. Pawar K, Chen Z, Shah NJ, Egan GF. Suppressing motion artefacts in MRI using an Inception‐ResNet network with motion simulation augmentation. NMR in Biomedicine. 2022;35(4):e4225. doi:10.1002/nbm.4225 [doi]
7. Li Y, Cheng C-C, Dubey J, Guenette JP, Qin L, Madore B. Head motion correction based on Pilot Tone signals – a referenceless method. In: Proceedings of the International Society of Magnetic Resonance in Medicine, Honolulu, HI. 2025;p. 4429.
8. Solomon E, Rigie DS, Vahle T, et al. Free-breathing radial imaging using a pilot-tone radiofrequency transmitter for detection of respiratory motion. Magn Reson Med,2021;85(5):2672-2685. doi: 10.1002/mrm.28616 [doi]
9. Klug T, Wang K, Ruschke S, Heckel R. Motionttt: 2d test-time-training motion estimation for 3d motion corrected mri. Advances in Neural Information Processing Systems. 2024;37:40615-50.
10. Souza R, Lucena O, Garrafa J, Gobbi D, Saluzzi M, Appenzeller S, et al. An open, multi-vendor, multi-field-strength brain MR dataset and analysis of publicly available skull stripping methods agreement. NeuroImage. 2018;170:482-94. doi:10.1016/j.neuroimage.2017.08.021 [doi]

Cite this abstract

http://echo.ismrm.org/p/ISMRM2026/661-03-014